AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography

Bowen Shi, Weiwei Cao, Ruifeng Yuan, Wanxing Chang, Wenrui Dai, Hongkai Xiong, Ling Zhang, Jianpeng Zhang

ICML 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace plain CNN encoder with CNN-ViT hybrid encoder (ablation)CT-DiagVLM base model · CT-RATEAUC: 79.3 -> 80.3Improved
add hybrid encoder when disease loss and prompt are already enabled (ablation)CT-DiagVLM · CT-RATEAUC: 83.2 -> 84.4Improved
add diagnosis-aware prompt strategy on top of hybrid encoder (ablation)CT-DiagVLM · CT-RATEAUC: 80.3 -> 82.4Improved
use handcrafted prompt refinement instead of diagnosis-aware prompt (ablation)CT-DiagVLM · CT-RATEAUC: 80.3 -> 81.0Improved
add disease-level contrastive learning (ablation)CT-DiagVLM · CT-RATEAUC: 82.4 -> 84.4Improved
use per-disease contrastive loss instead of coarse disease co-occurrence matching (ablation)CT-DiagVLM · CT-RATEAUC: 83.2 -> 84.4Improved
add DeepStack to hybrid encoder (ablation)CT-DiagVLM · CT-RATEAUC: 84.4 -> 84.0Hurt
add organ-level MoE to hybrid encoder (ablation)CT-DiagVLM · CT-RATEAUC: 84.4 -> 84.4No clear effect
initialize ViT from pre-trained SigLIP2 instead of from scratch (ablation)CT-DiagVLM hybrid encoder · CT-RATEAUC: 76.5 -> 84.4Improved
use larger SigLIP2 So-400M or medical MedSigLIP instead of SigLIP2 Base (ablation)CT-DiagVLM hybrid encoder · CT-RATEAUC: 84.4 -> 84.2 (So-400M), 83.8 (MedSigLIP)No clear effect
increase number of retrieved reports M for disease prototypes to 500 or more (ablation)diagnosis-aware prompt · CT-RATEAUC: plateau at M>=500, peak 84.4Improved
CT-DiagVLM versus base model on 60-disease settingCT-DiagVLM · CT-RATE 60 diseasessensitivity: 72.0 -> 65.5Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy